基于可见光/近红外光谱的稻米质量快速无损检测研究
|
摘要
随着社会经济的发展和人民生活水平的提高,粮食供求的主要矛盾已经从数量的不充足转变为质量的不理想。因此,建立稻米质量快速无损检测方法,无论是在育种,还是在食品加工和农产品贸易中都有重要意义。本文以不确定性人工智能理论和化学计量学理论为基础,利用数字图像处理技术、光谱分析技术、小波分析和模式识别技术研究影响稻米食用品质的三种重要品质垩白、直链淀粉含量和陈化的快速无损检测方法。
为了提高机器视觉对垩白的识别精度与适应能力,在稻米垩白品质快速无损检测方面,主要研究了以下内容：
(1)构建了用于图像采集的计算机视觉系统。分别在透射光与反射光环境下研究了光源、电压、背景等因素对稻米图像质量的影响,从而确定了适合稻米图像采集的最佳环境条件,即透射光条件下的最佳拍摄条件为：电压水平为6.4V,光源为LED灯组,背景为浅蓝色；反射光条件下的最佳拍摄条件为：电压水平为6.0V,光源为LED灯组,背景为深蓝色。
(2)分析了透射光与反射光条件下采集的稻米图像的直方图,研究了合适的图像去噪方法与图像分割算法。通过不同色彩空间下彩色直方图与灰度直方图分析发现反射光下采集的图像的灰度分布适合稻米垩白区域的识别。设计了加权均值滤波模板,既消除了噪声,又保护了胚乳区与垩白区的边界。根据图像分割算法-最大类间方差法的适用范围确定了稻米图像在进行垩白识别时应截取的矩形区域的大小。
(3)研究了具有自适应能力的垩白识别算法。该方法以不确定性人工智能理论与云模型为基础,把垩白与非垩白定义为两个定性概念,以一个不对称云和一个对称云来分别表达垩白与非垩白,以两组数字特征分别描述垩白云与非垩白云。通过对比同一电压下人工目测法、固定阈值法,云分类法的垩白大小检测结果检验云分类法的精确度,试验结果表明,云分类法比人工目测法的精确度高,云分类法与固定阈值法(即准确值)的偏差的均值为0.97,人工目测法与固定阈值法(即准确值)的偏差的均值为1.93；通过对比不同电压下人工目测法、云分类法的垩白大小检测结果检验云分类法的适应性,试验结果表明,云分类法比人工目测法的适应性好,用云分类法计算不同电压下同一粒米的垩白大小的标准差均值为0.57,人工目测法为2.29。
为了建立稳定性好、预测精度高的稻米直链淀粉含量近红外光谱定量分析模型,在稻米直链淀粉含量快速检测方面,主要研究了以下内容：
(1)研究了光谱采集参数对稻米近红外光谱响应特性的影响。通过对同一直链淀粉含量的稻米在不同参数下采集的光谱的统计分析,确定最佳采集参数为：扫描次数为64,分辨率为8cm-1,室内温度为15℃。
(2)研究了稻米异常光谱剔除方法和光谱预处理方法。为了优化校正集,提高模型的预测精度,用基于马氏距离准则和基于预测浓度残差准则相结合的方法剔除了18条因各种主客观因素产生的异常光谱。为了消除由于基线的漂移与偏移、仪器的随机噪声、杂散光等对光谱产生干扰,提高光谱的信噪比,采用多种方法对稻米光谱进行预处理,并比较了这些方法对建模结果的影响。通过模型评价指标的比较,确定用原光谱经一阶导数与SG卷积滤波相结合的方法进行光谱预处理。
(3)研究了定量分析方法对建模效果的影响。分别用逐步多元线性回归、主成分回归和偏最小二乘回归三种定量分析方法对经导数与SG卷积滤波处理后光谱建立校正模型。比较各项模型评价指标发现,偏最小二乘回归(PLS)方法建立的校正模型稳定性最好,预测值与标准值的相关系数最高,预测均方差最小。预测值与标准值相关系数为98.96%,校正均方差为0.62,预测均方差为1.19,交叉检验均方差为1.58。
为了建立陈化稻米近红外光谱定性识别模型,本文主要研究了以下内容：(1)研究了陈化米和非陈化米的近红外光谱响应特性,并利用主成分分析法结合马氏距离研究了不同光谱预处理方法对聚类效果的影响,一方面确定了用稻米的近红外光谱进行定性识别的可行性；另一方面,综合考虑类内距离小,类间距离大的聚类原则,最终选择不经任何处理的原光谱参加建模。
(2)研究了有效的光谱特征提取方法。用小波分析不仅能提取敏感的光谱特征信息,而且能够有效的降低高维空间数据,与支持向量机结合而成的新方法是一种有效的识别方法。利用db6小波变换得到的77个小波系数作为支持向量机模型的输入。当分解尺度为5时,数据点数由原来的2127个减少至77个
(3)研究了支持向量机的模型参数选择。首先用没有内部参数的线性函数作为核函数,改变惩罚因子C,以获得最小的MSE为准则,确定了最佳的误差惩罚因子C的值为1000；然后以不同的核函数以及核函数的内部参数建立支持向量机模型,通过试验发现当核函数为径向基函数,其参数γ为16时,所建立的模型识别率达98.45%。
With the development of social economy and the enhancement of living standards, principal contradiction between rice supply and demand was transformed from insufficient quantity to unfavourable quality. Therefore, it was significant to establish rapid rice quality detection method for the purpose of rice breeding, food processing and trade in agriculture.
Chalkiness, amylose content and aging of rice have key influence on edible quality of rice. Therefore, in this paper, rapid detection methods for these three characters were studied based on uncertainty artificial intelligence and Chemometrics theory, using digital image processing technology, spectral analysis technology, wavelet analysis and pattern recognition technology.
In order to improve identification accuracy and adaptability for chalkiness in computer vision system, the main content about chalkiness rapid detection method were as follows:
(1) Image acquisition environment under visible light was established. A computer vision system for image acquisition was set up, analyzing such factors on rice image quality as light source, voltage, and background, and finally the best environmental condition for rice image acquisition was determined. Under transmission light, the best voltage was 6.4V, the best light was LED and the background color was light blue. Under reflected light, the best voltage was 6.0V, the best light is LED and the background color was deep blue.
(2) Histogram of the paddy rice image acquired under the transmitted light and the reflected light was analyzed, the appropriate image denoising method and image segmentation algorithm were studied. The result of analyzing histogram of different color space showed that the gray scale distribution of image collected under the reflected light was suitable for chalkiness recognition. Weighted average value filter template was designed in order to not only eliminate the noise but also protect the boundary. The image segmentation algorithm-ostu method was discussed and the rice image rectangular region size was determined based on it.
(3) The adaptive chalkiness recognition algorithm was studied. This method was introduced on the basis of the uncertainty artificial intelligence theory and the cloud model. In this method, chalkiness and non-chalkiness were defined as two qualitative concepts, and then they were expressed by an asymmetrical cloud and a symmetrical cloud separately. Chalkiness cloud and non-chalkiness cloud were described by two groups of digital characteristics. Artificial estimation method, the fixed threshold method and the cloud classification method were used in chalkiness area detection under the same voltage value to test the accuracy of cloud classification method. The result showed that the cloud classification's precision was higher than artificial estimation method, because the average value of deviation between cloud classification and fixed threshold method (i.e. accurate value) was 0.97, while average value of deviation between artificial estimation method and fixed threshold method(i.e. accurate value) was 1.93. Artificial estimation method and cloud classification method were used in chalkiness area detection under the different voltage value to test the adaptability of cloud classification method. The result showed that the cloud classification method's adaptability was better than the artificial estimation method.
In order to establish the near-infrared spectrum quantitative analysis model with good stability and high prediction precision for paddy rice amylose content, the content mainly studied were as follows:
(1) The influence of spectrum collecting parameter to the paddy rice near-infrared spectral response characteristic was studied. The spectrums were collected for paddy rice with the same amylose content under the different parameter. The best collecting parameter was determined according to the result of spectrum statistical analysis. The scanning times was 64, the resolution was 8cm"1, and the indoor temperature was 15℃
(2) Abnormal spectrum removing method and the spectrum pretreatment method were studied for rice spectrums. In order to optimize the calibration set of sample and enhance the precision of the model,18 abnormal spectrums which were produced from subjective and objective factors were removed from calibration sample set based on mahalanobis distance and forecast concentration residual criterion. The factors such as baseline drift and shift, instrument's random noise, the stray light had disturbance to the spectrum. In order to eliminate disturbance and improve signal-to-noise ratio, many kinds of methods were used to process the paddy rice spectrums and their influence to model result were compared. The first derivative combined with the SG convolution smoothing method was determined through comparison of model evaluation index.
(3)The influence of quantitative analysis method to the model effect was studied. Multiple linear stepwise regression, principal component regression and partial least square regression were used to develop models on spectrums processed by first derivative combined with the SG convolution smoothing method. The model developed by partial least square regression resulted in the best stability, the highest correlation coefficient of the predicted value and the actual value, and the smallest root mean square error of prediction. The correlation coefficient of the predicted value and the actual value was 98.96%, the root mean square error of calibration was 0.62, the root mean square error of prediction was 1.19, and the root mean square error of cross validation was 1.58.
In order to study the potential of near-infrared reflectance spectroscopy for detecting aging rice, the main content about aging rice rapid detection method are as follows:
(1) The near-infrared spectral response characteristic of the aging rice and the non-aging rice were studied. The influence of different spectrum pretreatment method to the cluster effect was studied using the principal components analysis. The results showed that it was feasible to use paddy rice's near-infrared spectrums to recognize aging rice qualitatively. Original spectrums were selected to participate in the model according to the cluster principle that the distance in class was the smallest and the distance between classes was the biggest.
(2) The effective characteristic extraction method was studied for spectrums of rice. Wavelet analysis could not only withdraw the sensitive signature information of spectrum, but also reduce the dimension of data effectively. Therefore, wavelet analysis combined with support vector machine method provided an effective pattern recognition method.77 wavelet coefficients which obtained from the db6 wavelet transformation were taken as the input of the support vector machine model. When the decomposition size is 5, the number of data points of each spectrum was reduced from 2127 to 77.
(3) The parameter choice of support vector machine model was studied. Firstly, linear function was took as the nuclear function without internal parameter, and the model was developed with changing value of penalty factor. The results showed that the best value of error punishment factor C was 1000. Secondly, support vector machine model was developed using different nuclear function as well as the nuclear function's internal parameter. The experiment results showed that the identification accuracy was 98.45%when the nuclear function is the redial basis function and its parameterγis 16.
为了提高机器视觉对垩白的识别精度与适应能力,在稻米垩白品质快速无损检测方面,主要研究了以下内容：
(1)构建了用于图像采集的计算机视觉系统。分别在透射光与反射光环境下研究了光源、电压、背景等因素对稻米图像质量的影响,从而确定了适合稻米图像采集的最佳环境条件,即透射光条件下的最佳拍摄条件为：电压水平为6.4V,光源为LED灯组,背景为浅蓝色；反射光条件下的最佳拍摄条件为：电压水平为6.0V,光源为LED灯组,背景为深蓝色。
(2)分析了透射光与反射光条件下采集的稻米图像的直方图,研究了合适的图像去噪方法与图像分割算法。通过不同色彩空间下彩色直方图与灰度直方图分析发现反射光下采集的图像的灰度分布适合稻米垩白区域的识别。设计了加权均值滤波模板,既消除了噪声,又保护了胚乳区与垩白区的边界。根据图像分割算法-最大类间方差法的适用范围确定了稻米图像在进行垩白识别时应截取的矩形区域的大小。
(3)研究了具有自适应能力的垩白识别算法。该方法以不确定性人工智能理论与云模型为基础,把垩白与非垩白定义为两个定性概念,以一个不对称云和一个对称云来分别表达垩白与非垩白,以两组数字特征分别描述垩白云与非垩白云。通过对比同一电压下人工目测法、固定阈值法,云分类法的垩白大小检测结果检验云分类法的精确度,试验结果表明,云分类法比人工目测法的精确度高,云分类法与固定阈值法(即准确值)的偏差的均值为0.97,人工目测法与固定阈值法(即准确值)的偏差的均值为1.93；通过对比不同电压下人工目测法、云分类法的垩白大小检测结果检验云分类法的适应性,试验结果表明,云分类法比人工目测法的适应性好,用云分类法计算不同电压下同一粒米的垩白大小的标准差均值为0.57,人工目测法为2.29。
为了建立稳定性好、预测精度高的稻米直链淀粉含量近红外光谱定量分析模型,在稻米直链淀粉含量快速检测方面,主要研究了以下内容：
(1)研究了光谱采集参数对稻米近红外光谱响应特性的影响。通过对同一直链淀粉含量的稻米在不同参数下采集的光谱的统计分析,确定最佳采集参数为：扫描次数为64,分辨率为8cm-1,室内温度为15℃。
(2)研究了稻米异常光谱剔除方法和光谱预处理方法。为了优化校正集,提高模型的预测精度,用基于马氏距离准则和基于预测浓度残差准则相结合的方法剔除了18条因各种主客观因素产生的异常光谱。为了消除由于基线的漂移与偏移、仪器的随机噪声、杂散光等对光谱产生干扰,提高光谱的信噪比,采用多种方法对稻米光谱进行预处理,并比较了这些方法对建模结果的影响。通过模型评价指标的比较,确定用原光谱经一阶导数与SG卷积滤波相结合的方法进行光谱预处理。
(3)研究了定量分析方法对建模效果的影响。分别用逐步多元线性回归、主成分回归和偏最小二乘回归三种定量分析方法对经导数与SG卷积滤波处理后光谱建立校正模型。比较各项模型评价指标发现,偏最小二乘回归(PLS)方法建立的校正模型稳定性最好,预测值与标准值的相关系数最高,预测均方差最小。预测值与标准值相关系数为98.96%,校正均方差为0.62,预测均方差为1.19,交叉检验均方差为1.58。
为了建立陈化稻米近红外光谱定性识别模型,本文主要研究了以下内容：(1)研究了陈化米和非陈化米的近红外光谱响应特性,并利用主成分分析法结合马氏距离研究了不同光谱预处理方法对聚类效果的影响,一方面确定了用稻米的近红外光谱进行定性识别的可行性；另一方面,综合考虑类内距离小,类间距离大的聚类原则,最终选择不经任何处理的原光谱参加建模。
(2)研究了有效的光谱特征提取方法。用小波分析不仅能提取敏感的光谱特征信息,而且能够有效的降低高维空间数据,与支持向量机结合而成的新方法是一种有效的识别方法。利用db6小波变换得到的77个小波系数作为支持向量机模型的输入。当分解尺度为5时,数据点数由原来的2127个减少至77个
(3)研究了支持向量机的模型参数选择。首先用没有内部参数的线性函数作为核函数,改变惩罚因子C,以获得最小的MSE为准则,确定了最佳的误差惩罚因子C的值为1000；然后以不同的核函数以及核函数的内部参数建立支持向量机模型,通过试验发现当核函数为径向基函数,其参数γ为16时,所建立的模型识别率达98.45%。
With the development of social economy and the enhancement of living standards, principal contradiction between rice supply and demand was transformed from insufficient quantity to unfavourable quality. Therefore, it was significant to establish rapid rice quality detection method for the purpose of rice breeding, food processing and trade in agriculture.
Chalkiness, amylose content and aging of rice have key influence on edible quality of rice. Therefore, in this paper, rapid detection methods for these three characters were studied based on uncertainty artificial intelligence and Chemometrics theory, using digital image processing technology, spectral analysis technology, wavelet analysis and pattern recognition technology.
In order to improve identification accuracy and adaptability for chalkiness in computer vision system, the main content about chalkiness rapid detection method were as follows:
(1) Image acquisition environment under visible light was established. A computer vision system for image acquisition was set up, analyzing such factors on rice image quality as light source, voltage, and background, and finally the best environmental condition for rice image acquisition was determined. Under transmission light, the best voltage was 6.4V, the best light was LED and the background color was light blue. Under reflected light, the best voltage was 6.0V, the best light is LED and the background color was deep blue.
(2) Histogram of the paddy rice image acquired under the transmitted light and the reflected light was analyzed, the appropriate image denoising method and image segmentation algorithm were studied. The result of analyzing histogram of different color space showed that the gray scale distribution of image collected under the reflected light was suitable for chalkiness recognition. Weighted average value filter template was designed in order to not only eliminate the noise but also protect the boundary. The image segmentation algorithm-ostu method was discussed and the rice image rectangular region size was determined based on it.
(3) The adaptive chalkiness recognition algorithm was studied. This method was introduced on the basis of the uncertainty artificial intelligence theory and the cloud model. In this method, chalkiness and non-chalkiness were defined as two qualitative concepts, and then they were expressed by an asymmetrical cloud and a symmetrical cloud separately. Chalkiness cloud and non-chalkiness cloud were described by two groups of digital characteristics. Artificial estimation method, the fixed threshold method and the cloud classification method were used in chalkiness area detection under the same voltage value to test the accuracy of cloud classification method. The result showed that the cloud classification's precision was higher than artificial estimation method, because the average value of deviation between cloud classification and fixed threshold method (i.e. accurate value) was 0.97, while average value of deviation between artificial estimation method and fixed threshold method(i.e. accurate value) was 1.93. Artificial estimation method and cloud classification method were used in chalkiness area detection under the different voltage value to test the adaptability of cloud classification method. The result showed that the cloud classification method's adaptability was better than the artificial estimation method.
In order to establish the near-infrared spectrum quantitative analysis model with good stability and high prediction precision for paddy rice amylose content, the content mainly studied were as follows:
(1) The influence of spectrum collecting parameter to the paddy rice near-infrared spectral response characteristic was studied. The spectrums were collected for paddy rice with the same amylose content under the different parameter. The best collecting parameter was determined according to the result of spectrum statistical analysis. The scanning times was 64, the resolution was 8cm"1, and the indoor temperature was 15℃
(2) Abnormal spectrum removing method and the spectrum pretreatment method were studied for rice spectrums. In order to optimize the calibration set of sample and enhance the precision of the model,18 abnormal spectrums which were produced from subjective and objective factors were removed from calibration sample set based on mahalanobis distance and forecast concentration residual criterion. The factors such as baseline drift and shift, instrument's random noise, the stray light had disturbance to the spectrum. In order to eliminate disturbance and improve signal-to-noise ratio, many kinds of methods were used to process the paddy rice spectrums and their influence to model result were compared. The first derivative combined with the SG convolution smoothing method was determined through comparison of model evaluation index.
(3)The influence of quantitative analysis method to the model effect was studied. Multiple linear stepwise regression, principal component regression and partial least square regression were used to develop models on spectrums processed by first derivative combined with the SG convolution smoothing method. The model developed by partial least square regression resulted in the best stability, the highest correlation coefficient of the predicted value and the actual value, and the smallest root mean square error of prediction. The correlation coefficient of the predicted value and the actual value was 98.96%, the root mean square error of calibration was 0.62, the root mean square error of prediction was 1.19, and the root mean square error of cross validation was 1.58.
In order to study the potential of near-infrared reflectance spectroscopy for detecting aging rice, the main content about aging rice rapid detection method are as follows:
(1) The near-infrared spectral response characteristic of the aging rice and the non-aging rice were studied. The influence of different spectrum pretreatment method to the cluster effect was studied using the principal components analysis. The results showed that it was feasible to use paddy rice's near-infrared spectrums to recognize aging rice qualitatively. Original spectrums were selected to participate in the model according to the cluster principle that the distance in class was the smallest and the distance between classes was the biggest.
(2) The effective characteristic extraction method was studied for spectrums of rice. Wavelet analysis could not only withdraw the sensitive signature information of spectrum, but also reduce the dimension of data effectively. Therefore, wavelet analysis combined with support vector machine method provided an effective pattern recognition method.77 wavelet coefficients which obtained from the db6 wavelet transformation were taken as the input of the support vector machine model. When the decomposition size is 5, the number of data points of each spectrum was reduced from 2127 to 77.
(3) The parameter choice of support vector machine model was studied. Firstly, linear function was took as the nuclear function without internal parameter, and the model was developed with changing value of penalty factor. The results showed that the best value of error punishment factor C was 1000. Secondly, support vector machine model was developed using different nuclear function as well as the nuclear function's internal parameter. The experiment results showed that the identification accuracy was 98.45%when the nuclear function is the redial basis function and its parameterγis 16.
引文
1.包晓敏,汪亚明,黄振坌.计算机视觉技术在大米轮廓检测上的应用.浙江工程学院学报,2003,20(2)：104-107
2.陈斌,邹贤勇,朱文静.PCA结合马氏距离法剔除近红外异常样品.江苏大学学报(自然科学版),2008,29(04)：277-279
3.陈春燕.籼稻直链淀粉和蛋白质含量的快速活体定标研究.[硕士学位论文].重庆：西南大学,2008
4.陈建华,姚青,胡洁等.基于计算机视觉的稻米垩白检测方法研究.计算机工程与设计,2010,31(01)：218-224
5.陈建伟,刘璎瑛.基于机器视觉技术的大米品质检测综述.粮食与食品工业,2008,15(03)：44-47
6.陈兰珍.蜂蜜品质近红外光谱评价技术研究.[博士学位论文].北京：中国农业科学院,2010
7.陈鲤江,刘铁根,马金英等.一种区域分离方法及其在米粒检测中的应用.光电子·激光,2006,17(07)：867-870
8.陈玲.基于支持向量机的多类文本分类研究.[硕士学位论文].重庆：重庆大学,2010
9.陈晓玲,冯前进,谢振文等.水稻直链淀粉含量近红外模型的创建.仲恺农业工程学院学报,2009,22(1)：5-8
10.陈永艳,闸建文.种子实物扫描图像特性研究.山东理工大学学报(自然科学版),2003,17(1)：43-45
11.成芳.稻种质量的机器视觉无损检测研究.[博士学位论文].杭州：浙江大学,2004
12.崔改泵.稻米直链淀粉含量快速检测方法的试验研究.[硕士学位论文].中国农业大学,2004
13.付忠良.图像阈值选取方法的构造.中国图像图形学报,2000,5(6)：466-469
14.耿珍,王卫星.基于多重色彩转换和模糊阈值的垩白检测.计算机工程与应用,2008,44(29)：207-210
15.龚声蓉,刘纯平,王强等.数字图像处理与分析.北京：清华大学出版社.2006,62-65
16.韩占江,王伟华,李帅.几种大米新陈度检验方法的比较研究.湖北农业科学,2009,48(7)：1736-1742
17.何东健.数字图像处理.陕西：西安电子科技大学出版社,2003,67-68
18.侯彩云,Seiichi, Oshita.3维图像处理系统在稻米品质检测中的应用研究.农业工程学报,2001,17(3)：92-95
19.侯彩云,王启辉,黄训文,傅泽田.陈化稻米数字图像检测方法的研究.中国粮油学报,2008,23(4)：194-196
20.侯彩云,王一鸣,凌云等.垩白米粒的计算机图像识别.农业工程学报,2002,18(3)：165-168
21.侯彩云.米及其功能.粮食与食品工业,2003,(2)：14-16.
22.黄光华,余擎宇.解读三项新粮食储存品质判定规则国家标准.粮油仓储科技通讯,2007,(6)：40-41
23.黄星奕,李剑,姜松.基于计算机视觉的稻谷品种识别技术的研究.江苏大学学报(自然科学版),2004,25(2)：102-104
24.黄星奕,吴守一,方如明.基于小波变换的稻米爆腰检测技术研究.农业工程学报,2004,20(6)：194-196
25.黄星奕,吴守一,方如明等.遗传神经网络在稻米垩白度检测中的应用研究.农业工程学报,2003,19(3)：137-139
26.菅维乐,姜威.基于多分辨率分析的数字图像自动聚焦算法研究.计量技术,2004,(6)：3-5
27.蒋建兵,梁家荣,江伟等.梯形云模型在概念划分及提升中的应用.计算机工程与设计,2008,29(5)：1235-1240
28.李德毅,杜鹢.不确定性人工智能.北京：国防工业出版社,2005
29.李德毅,刘常昱,杜鹢等.不确定性人工智能.软件学报.2004,15(11)：1583-1594
30.李德毅,刘常昱.论正态云模型的普适性.中国工程科学,2004,6(8)：91-97
31.李德毅,孟海军,史雪梅.隶属云和隶属云发生器.计算机研究与发展.1995,32(6)：32-41
32.梁逸曾,俞汝勤.分析化学手册--化学计量学.北京：化工出版社,2001
33.凌云,王一鸣,孙明等.基于分形维数的垩白米图像检测方法.农业机械学报,2005,36(7)：92-95
34.凌云,王一鸣,孙明等.基于机器视觉的大米外观品质检测装置.农业机械学报,2005,36(9)：89-921
35.凌云.基于机器视觉的谷物外观品质检测技术研究.[博士学位论文].北京：中国农业大学,2004
36.刘长荣,赵军陈.陈化粮的成因及应采取的对策.农金纵横,2000,(05)：41.42
37.刘国信.警惕陈化米“化妆”流入市场.大众标准化,2005,(05)：30-31
38.刘建学.实用近红外光谱分析技术.北京：科学出版社,2008
39.刘强,罗长兵,陈绍江等.近红外光谱分析青贮玉米NDF中判别异常光谱的研究.光谱学与光谱分析,2007,27(8)：1514-1518
40.刘蓉,陈文亮,徐可欣等.奇异点快速检测在牛奶成分近红外光谱测量中的应用.光谱学与光谱分析,2005,25(2)：207-210
41.刘宜柏,黄英金.稻米食味品质的相关性研究.江西农业大学学报,1989,11(4)：1-5
42.刘璎瑛,丁为民,陈建伟等.基于霍特林变换的稻米彩色图像粒形检测算法.中国水稻科学,2010,24(3)：325-328
43.陆辉山.水果内部品质可见/近红外光谱实时无损检测关键技术研究.[博士学位论文].杭州：浙江大学,2006
44.陆艳婷,金庆生,叶胜海等.应用近红外光谱技术快速测定粳稻品种的直链淀粉含量.中国粮油学报,2007,(03)：149-153
45.陆艳婷,张小明,叶胜海等.稻米品质近红外光谱法分析中定标样品选择与模型优化.核农学报,2008,22(6)：823-828
46.路峰,吴慧中.网格环境下基于云模型的信任评估与决策方法研究.系统仿真学报,2009,21(2)：421-426
47.吕季璋.大米新陈度快速检测的研究.中国粮油学报,1991,6(3)：15-18
48.马文杰.烟叶图像采集技术规范与烤烟收购质量分级特征研究.[博士学位论文].武汉：华中农业大学,2007
49.闵顺耕,李宁,张明祥.近红外光谱分析中异常值的判别与定量模型优化.光谱学与光谱分析,2004,24(10)：1205-1209
50.倪美仙.稻米新陈度的分光光度法测定.西部粮油科技,1997,(03)：39-40
51.史波林,赵镭,刘文等.苹果内部品质近红外光谱检测的异常样本分析.农业机械学报,2010,41(2)：132-137
52.舒庆尧,吴殿星,夏英武等.用近红外反射光谱技术测定精米粉样品表观直链淀粉含量的研究.中国水稻科学,1999,13(3)：189-192
53.孙成效,段彬伍,谢黎虹.利用近红外透射光谱技术同步测定糙米的多项品质指标初报.中国水稻科学,2006,20(4)：451-454
54.孙翠霞,方华,胡波.基于灰度图像的大米垩白检测算法研究.广西工学院学报(自然科学版),2010,21(2)：36-40
55.孙明,凌云,王一鸣.在MATLAB环境中基于计算机视觉技术的大米垩白检测.农业工程学报,2002,18(2)：146-149
56.孙明,石庆兰,孙红等.基于计算机视觉的大米外观品质检测.沈阳农业大学学报,2005,36(6)：659-662
57.唐为民,呼玉山.稻米陈化对品质的影响及陈化机理.中国食物与营养,2004,(4)：7-10
58.田海清.西瓜品质可见/近红外光谱无损检测技术研究.[博士学位论文].杭州：浙江大学,2006
59.万鹏.大米陈化度快速检测系统的研究与开发.[硕士学位论文].长春：吉林大学,2006
60.王卫星,刘永强.基于直方图修正的小波自适应阈值大米垩白分割.重庆邮电大学学报(自然科学版),2010,22(2)：218-222
61.王仪春,张小明,石春海.稻米直链淀粉含量测定方法的探讨.中国农学通报,2001,17(5)：30-32
62.王友华,马雷.美国稻米分级标准与检测技术研究.粮食饲料与工业,2007,(04)：5-8
63.王展,梁秋慧,刘英.大米新鲜度快速检测方法研究.粮食与饲料工业,2007,(03)：5-6
64.王佐成,李永树,薛丽霞等.基于云模糊理论的图像纹理分割.西南交通大学学报,2007,42(5)：548-552
65.吴建国,刘长东,杨国花等.基于计算机视觉的稻米垩白指标快速测定方法研究.作物学报,2005,31(5)：670-672
66.吴兰兰.基于数字图像处理的玉米苗期田间杂草的识别研究.[博士学位论文].武汉：华中农业大学,2010
67.吴彦红,刘木华,杨君等.基于计算机视觉的大米外观品质检测.农业机械学报,2007,38(7)：107-111
68.萧嵘,王继成,张福炎.支持向量机理论综述.计算机科学,2000,(03)：1-3.
69.肖昕,陈奕,罗文永等.单粒活体稻谷种子直链淀粉含量的近红外透射光谱分析.中国水稻科学,2003,(03)：287-290
70.谢新华.稻米中直链淀粉和蛋白质含量的近红外透射光谱预测研究.[硕士学位论文].西北农林科技大学,2004
71.严衍禄.近红外光谱分析基础与应用.北京：中国轻工业出版社,2005
72.于润伟,朱晓慧.基于图像处理的稻米垩白自动检测研究.中国粮油学报,2007,22(1)：122-125
73.于晓娟,代冬岩,邓发强.模极大值法与尺度独立法在稻米边缘检测中的模拟研究.黑龙江八一农垦大学学报,2009,(03)：98-100
74.喻擎苍,严红滨.一种基于图像轮廓线的稻种模糊识别方法.农业工程学报,2002,18(1)：150-153
75.张聪,张慧.基于数学形态学的稻米粒形边缘检测研究.中国粮油学报,2007,22(5)：139-141
76.张静.几种检测大米新鲜度的方法比较.啤酒科技,2003,(8)：27-29
77.张永.基于模糊支持向量机的多类分类算法研究.[博士学位论文].大连：大连理工大学,2008
78.郑华东,刘木华,吴彦红等.基于计算机视觉的大米裂纹检测研究.农业工程学报,2006,22(7)：129-133
79.周福生.评价大米质量的基本内容.粮食科技与经济,1998,(5)：35-36
80.朱蔚萍,靳宏磊,叶桦等.二维灰度直方图上的距离判断分割方法.东南大学学报,1999,29(S)：16-19
81.诸小立,袁洪福,王艳斌等.近红外稳健分析校正模型的建立—样品温度的影响.光谱学与光谱分析,2004,24(6)：666-671
82.祝诗平,王一鸣,张小超等.基于遗传算法的近红外光谱谱区选择方法.农业机械学报,2004,35(5)：152-156
83.祝诗平,王一鸣,张小超等.近红外光谱建模异常样品剔除准则与方法.农业机械学报,2004,35(4)：115-119
84.祝晓芳,侯彩云,芮闯.基于计算机图像处理技术的黄粒米检测系统研究.粮油食品科技,2008,16(4)：6-8
85. Aggarwal A K, Mohan R. Aspect ratio analysis using image processing for rice grain quality. J Food Eng,2010,6(05):251-257
86. Bo-Jein K. The robustness of different statistical models for prediction of amylose content of rice based on near-infrared spectroscopy. J Agr As,2001,2(5):464-474
87. Camargo A, Smith. J S. Image pattern classification for the identification of disease causing agents in plants. Comp Electr Agr,2009,66:121-125
88. Chen C L, Chen T F. Analysing the freshness of intact rice grains by colour determination of peroxidase activity. J Sci FoodAgr,2003,83(12):1214-1218
89. Chen J H, Guan Z X, Sun C X et al. Inspection of rice appearance quality using machine vision. Proceedings of the 2009 WRI Global Congress on Intelligent Systems,2009, China
90. Cho K, Meer P. Image segmentation from consensus information. Comp Vis Im Und,1997,68(1):72-89
91. Christiane C, Fertig, Fridrun P, Roger D. Feasibility study for the rapid determination of the amylose content in starch by near-infrared spectroscopy. Eur J Pharm Sci,2004,21:155-159
92. Cozzolino D, Fassio A, Restaino E, et al. Verification of silage type using near-infrared spectroscopy combined with multivariate analysis. Journal of Agr and Food Chem,2008,56 (1):79-83
93. David M, Haaland, Edward V, Thomas. Partial least-squares methods for spectral analyses:Relation to other quantitaive calibration methods and the extraction of qualitative information. An Chem,1988,60 (11):1193-1202
94. Delwiche S R, Bean M M. Apparent amylose content of milled rice by near-inf rared reflectance spectrophotometry. Cer Chem,1995,72(2):182-187
95. Emadzadeh B, Razavi S M A, Farahmandfar R. Monitoring geometric characteristics of rice during processing by image analysis system and micrometer measurement. Int Agrophys,2010,24(l):21-27
96. Fuller M P, Ritter G L, Draper C S. Partial least squares quantitative analysis of infrared spectroscopic data. Part I:Algorithm implementation. Appl Spectr,1988, 42 (2):217-227
97. Gao H, Wang Y Q, Ge P J. Rice shape parameter detection based on image processing.1st International Conference on Computer and Computing Technologies in Agriculture,2007, China
98. Hachiya M, Asanome N, Goto T et al. Fluorescence Imaging with UV-Excitation for Evaluating Freshness of Rice. JARQ-Jpn Agr Res Q,2009,43(3):193-198
99. Jinorose M, Prachayawarakorn S, Soponronnarit S. Development of a computer vision system and novel evaluation criteria to characterize color and appearance of rice. Dry Tech,2010,28(9):1118-1124
100.Jouan R, Imbaud D, Bouveresse E, Massart D L, et al. Detection of prediction outliers and inliers in multivariate calibration. An Chim Acta,1999,388(3): 283-301
101.Khazaei J, Golpour I, Gholami A. Paddy rice varieties recognition using computer vision and neural networks.2010 International Conference on Agricultural and Animal Science,2010, Singapore
102.Lan Y, Fang Q, Kocher M F, Hanna M A. Detection of fissures in rice grains using imaging enhancement. Int J Food Prop,2002,5(01):205-215
103.Lee J C, Yoon Y H, Kim S M, Pyo B S, Hsieh F H, Kim H J, Eun J B, Rapid prediction of amylose content of polished rice by Fourier transform near-infrared spectroscopy. Food Sci Biotech,2007,16(3):477-481
104.Li D Y, Han J W, Shi X M, Chan M C. Knowledge representation and discovery based on linguistic atoms. J Knowledge-Based Syst,1998(10):431-440
105.Lin P, Chen, Y M, Bao Y D, He Y. Image detection of rice fissures using biorthogonal B-Spline wavelets in multi-resolution spaces. Food Biop Tech,2010, (06):1-8
106.Liu C C, Shaw J T, Poong K Y, et al. Classifying paddy rice by morphological and color features using machine vision. Cer Che,2005,82(06):649-653
107.Liu G R. Rice color inspection based on image processing technique. International Conference on Advances in Energy Engineering,2010, China
108.Lleti R, Melendeza E, OrtizM C, et al. Outliers in partial least squares regression application to calibration of wine grade with mean infrared data. An Chim Acta, 2005,544(1):60-701
109.Manickavasagan A, Sathya G et al. Comparison of illuminations to identify wheat classes using monochrome images. Comp El Agr,2008,63(2):237-244
110.Matsukura U, Kaneko S, Momma M. Method for measuring the freshness of individual rice grains by means of a color reaction of catalase activity. Nippon Shokuhin Kagaku Kogaku Kaishi,2000,47(7):523-528
111.Otsu N. A threshold selection method from gray-level histograms. IEEE T Syst Man Cy,1979,9(1):62-66
112.Pan M S, Tang J T, Yang X L. An Adaptive Median Filter Algorithm Based on B-spline Function. intl J Aut Comp,2011,8(1):92-99
113.Randall Mutters. Producing high quality rice for export market. USDA,2002.
114.Rittiron R, Saranwong S, Kawano S, Useful tips for constructing a near infrared-based quality sorting system for single brown-rice kernels. J Near Infrared Spectrosc.2004,(12):133-139
115.Sakai N, Yonekawa S, Matsuzaki A, et al. Two-dimensional image analysis of the shape of rice and its application to separating. J Food Eng,1996,27(04):397-407
116.Sansomboonsuk S, Afzulpurkar N. A computer vision system for rice kernel quality evaluation.16th International Symposium of the Danube-Adria-Association-for-Automation-and-Manufacturing,2005, Opatija, Croatia
117.Shao Y, Zhao C, He Y, Bao Y. Application of infrared spectroscopy technique and chemometrics for measurement of components in rice after radiation. Trans ASABE, 2009,52(1):187-192
118.Shimizu N, Okadome H, Yanagisawa T, Andren H, Thente K, Kimura T, Ohtsubo K. Application of visible/near-infrared transmittance spectroscopy for the improvement of amylose determination accuracy. Food Sci Tech Res,2003,9(2): 134-136
119.Shindo S, Takahashi S, Kobayashi M. A novel method for the determination of freshness of rice by acidification power test. Nippon Shokuhin Kagaku Kogaku Kaishi,2000,47(3):260-263
120.Takeda F, Uchida H, Tsuzuki T et al. A proposal of grading system for fallen rice using neural network. IEEE International Joint Conference on Neural Networks, 2002
121. Van D, Gerard. Colour analysis of rice using flatbed scanning and image Analysis 3rd European Conference on Colour in Graphics, Imaging, and Vision,2006
122.Vapnik V, Lerner A. Pattern recognition using generalized portrait. Aut Rem Contr, 1963,24 (6):774-780
123.Vapnik V. Statistical Learning Theory, Wiley, NY,1998
124.Verma B. Image processing techniques for grading and classification of rice. International Conference on Computer and Communication Technology,2010, India
125.Villarel C P, Cruz N M, Juliano B O. Rice amylose analysis by nearinfrared transmitance spect roscopy. Cer Chem,1994, (71):292-296
126.Visen N S, Shashidhar N S, Paliwal J, et al. Identification and segmentation of occluding groups of grain kernels in a grain sample image. JAgrie Eng Res,2001, 79(2):159-166
127.Walczak B, Massart D L. Robust principal components regression as a detection tool for outliers. Chem and Int Lab Syst,1995,27(1):41-54
128.Wan Y N, Lin C M, Chiou J F. Rice quality classification using an automatic grain quality inspection system. Tran ASAE,2002,45(2):379-387
129. Wan Y N. Adaptive classification method for an automatic grain quality inspection system using machine vision and neural network. ASAE Annual International Meeting,2000.
130. Wee C Y, Paramesran R, Takeda F. Sorting of rice grains using zernike moments. J Real time Im Proc,2009,4(04):353-363
131.Wu J G, Shi C H. Prediction of grain weight, brown rice weight and amylose content in single rice grains using near-infrared reflectance spectroscopy. Field Crops Res,2004,87(1):13-21
132.Xu L Z, Li Y M. Multi-Scale edge detection of rice internal damage based on computer vision. IEEE International Conference on Automation and Logistics, 2008, Qingdao, China
133.Xu L Z, Li Y M. Detection of stress cracks in rice kernels based on machine vision. Agr Mech in Asia, Africa and Latin America,2009,40(4):38-41
134.Yosuke Y, Hiroyoshi I, Minako T et al. Chalkiness in rice:Potential for evaluation with image analysis. Crop sci,2007,41(05):2113-2120
135.Zadeh L A. Fuzzysets. Inf Contr,1965, (8):338-353
136.Zhang Q, Yang W, Howard L, et al. Tracing fissure information by scanning elect ron m icro scopy characterization of naturally fissured surfaces of rice kernels. Trans ASAE,2003,46(6):1583-1588
2.陈斌,邹贤勇,朱文静.PCA结合马氏距离法剔除近红外异常样品.江苏大学学报(自然科学版),2008,29(04)：277-279
3.陈春燕.籼稻直链淀粉和蛋白质含量的快速活体定标研究.[硕士学位论文].重庆：西南大学,2008
4.陈建华,姚青,胡洁等.基于计算机视觉的稻米垩白检测方法研究.计算机工程与设计,2010,31(01)：218-224
5.陈建伟,刘璎瑛.基于机器视觉技术的大米品质检测综述.粮食与食品工业,2008,15(03)：44-47
6.陈兰珍.蜂蜜品质近红外光谱评价技术研究.[博士学位论文].北京：中国农业科学院,2010
7.陈鲤江,刘铁根,马金英等.一种区域分离方法及其在米粒检测中的应用.光电子·激光,2006,17(07)：867-870
8.陈玲.基于支持向量机的多类文本分类研究.[硕士学位论文].重庆：重庆大学,2010
9.陈晓玲,冯前进,谢振文等.水稻直链淀粉含量近红外模型的创建.仲恺农业工程学院学报,2009,22(1)：5-8
10.陈永艳,闸建文.种子实物扫描图像特性研究.山东理工大学学报(自然科学版),2003,17(1)：43-45
11.成芳.稻种质量的机器视觉无损检测研究.[博士学位论文].杭州：浙江大学,2004
12.崔改泵.稻米直链淀粉含量快速检测方法的试验研究.[硕士学位论文].中国农业大学,2004
13.付忠良.图像阈值选取方法的构造.中国图像图形学报,2000,5(6)：466-469
14.耿珍,王卫星.基于多重色彩转换和模糊阈值的垩白检测.计算机工程与应用,2008,44(29)：207-210
15.龚声蓉,刘纯平,王强等.数字图像处理与分析.北京：清华大学出版社.2006,62-65
16.韩占江,王伟华,李帅.几种大米新陈度检验方法的比较研究.湖北农业科学,2009,48(7)：1736-1742
17.何东健.数字图像处理.陕西：西安电子科技大学出版社,2003,67-68
18.侯彩云,Seiichi, Oshita.3维图像处理系统在稻米品质检测中的应用研究.农业工程学报,2001,17(3)：92-95
19.侯彩云,王启辉,黄训文,傅泽田.陈化稻米数字图像检测方法的研究.中国粮油学报,2008,23(4)：194-196
20.侯彩云,王一鸣,凌云等.垩白米粒的计算机图像识别.农业工程学报,2002,18(3)：165-168
21.侯彩云.米及其功能.粮食与食品工业,2003,(2)：14-16.
22.黄光华,余擎宇.解读三项新粮食储存品质判定规则国家标准.粮油仓储科技通讯,2007,(6)：40-41
23.黄星奕,李剑,姜松.基于计算机视觉的稻谷品种识别技术的研究.江苏大学学报(自然科学版),2004,25(2)：102-104
24.黄星奕,吴守一,方如明.基于小波变换的稻米爆腰检测技术研究.农业工程学报,2004,20(6)：194-196
25.黄星奕,吴守一,方如明等.遗传神经网络在稻米垩白度检测中的应用研究.农业工程学报,2003,19(3)：137-139
26.菅维乐,姜威.基于多分辨率分析的数字图像自动聚焦算法研究.计量技术,2004,(6)：3-5
27.蒋建兵,梁家荣,江伟等.梯形云模型在概念划分及提升中的应用.计算机工程与设计,2008,29(5)：1235-1240
28.李德毅,杜鹢.不确定性人工智能.北京：国防工业出版社,2005
29.李德毅,刘常昱,杜鹢等.不确定性人工智能.软件学报.2004,15(11)：1583-1594
30.李德毅,刘常昱.论正态云模型的普适性.中国工程科学,2004,6(8)：91-97
31.李德毅,孟海军,史雪梅.隶属云和隶属云发生器.计算机研究与发展.1995,32(6)：32-41
32.梁逸曾,俞汝勤.分析化学手册--化学计量学.北京：化工出版社,2001
33.凌云,王一鸣,孙明等.基于分形维数的垩白米图像检测方法.农业机械学报,2005,36(7)：92-95
34.凌云,王一鸣,孙明等.基于机器视觉的大米外观品质检测装置.农业机械学报,2005,36(9)：89-921
35.凌云.基于机器视觉的谷物外观品质检测技术研究.[博士学位论文].北京：中国农业大学,2004
36.刘长荣,赵军陈.陈化粮的成因及应采取的对策.农金纵横,2000,(05)：41.42
37.刘国信.警惕陈化米“化妆”流入市场.大众标准化,2005,(05)：30-31
38.刘建学.实用近红外光谱分析技术.北京：科学出版社,2008
39.刘强,罗长兵,陈绍江等.近红外光谱分析青贮玉米NDF中判别异常光谱的研究.光谱学与光谱分析,2007,27(8)：1514-1518
40.刘蓉,陈文亮,徐可欣等.奇异点快速检测在牛奶成分近红外光谱测量中的应用.光谱学与光谱分析,2005,25(2)：207-210
41.刘宜柏,黄英金.稻米食味品质的相关性研究.江西农业大学学报,1989,11(4)：1-5
42.刘璎瑛,丁为民,陈建伟等.基于霍特林变换的稻米彩色图像粒形检测算法.中国水稻科学,2010,24(3)：325-328
43.陆辉山.水果内部品质可见/近红外光谱实时无损检测关键技术研究.[博士学位论文].杭州：浙江大学,2006
44.陆艳婷,金庆生,叶胜海等.应用近红外光谱技术快速测定粳稻品种的直链淀粉含量.中国粮油学报,2007,(03)：149-153
45.陆艳婷,张小明,叶胜海等.稻米品质近红外光谱法分析中定标样品选择与模型优化.核农学报,2008,22(6)：823-828
46.路峰,吴慧中.网格环境下基于云模型的信任评估与决策方法研究.系统仿真学报,2009,21(2)：421-426
47.吕季璋.大米新陈度快速检测的研究.中国粮油学报,1991,6(3)：15-18
48.马文杰.烟叶图像采集技术规范与烤烟收购质量分级特征研究.[博士学位论文].武汉：华中农业大学,2007
49.闵顺耕,李宁,张明祥.近红外光谱分析中异常值的判别与定量模型优化.光谱学与光谱分析,2004,24(10)：1205-1209
50.倪美仙.稻米新陈度的分光光度法测定.西部粮油科技,1997,(03)：39-40
51.史波林,赵镭,刘文等.苹果内部品质近红外光谱检测的异常样本分析.农业机械学报,2010,41(2)：132-137
52.舒庆尧,吴殿星,夏英武等.用近红外反射光谱技术测定精米粉样品表观直链淀粉含量的研究.中国水稻科学,1999,13(3)：189-192
53.孙成效,段彬伍,谢黎虹.利用近红外透射光谱技术同步测定糙米的多项品质指标初报.中国水稻科学,2006,20(4)：451-454
54.孙翠霞,方华,胡波.基于灰度图像的大米垩白检测算法研究.广西工学院学报(自然科学版),2010,21(2)：36-40
55.孙明,凌云,王一鸣.在MATLAB环境中基于计算机视觉技术的大米垩白检测.农业工程学报,2002,18(2)：146-149
56.孙明,石庆兰,孙红等.基于计算机视觉的大米外观品质检测.沈阳农业大学学报,2005,36(6)：659-662
57.唐为民,呼玉山.稻米陈化对品质的影响及陈化机理.中国食物与营养,2004,(4)：7-10
58.田海清.西瓜品质可见/近红外光谱无损检测技术研究.[博士学位论文].杭州：浙江大学,2006
59.万鹏.大米陈化度快速检测系统的研究与开发.[硕士学位论文].长春：吉林大学,2006
60.王卫星,刘永强.基于直方图修正的小波自适应阈值大米垩白分割.重庆邮电大学学报(自然科学版),2010,22(2)：218-222
61.王仪春,张小明,石春海.稻米直链淀粉含量测定方法的探讨.中国农学通报,2001,17(5)：30-32
62.王友华,马雷.美国稻米分级标准与检测技术研究.粮食饲料与工业,2007,(04)：5-8
63.王展,梁秋慧,刘英.大米新鲜度快速检测方法研究.粮食与饲料工业,2007,(03)：5-6
64.王佐成,李永树,薛丽霞等.基于云模糊理论的图像纹理分割.西南交通大学学报,2007,42(5)：548-552
65.吴建国,刘长东,杨国花等.基于计算机视觉的稻米垩白指标快速测定方法研究.作物学报,2005,31(5)：670-672
66.吴兰兰.基于数字图像处理的玉米苗期田间杂草的识别研究.[博士学位论文].武汉：华中农业大学,2010
67.吴彦红,刘木华,杨君等.基于计算机视觉的大米外观品质检测.农业机械学报,2007,38(7)：107-111
68.萧嵘,王继成,张福炎.支持向量机理论综述.计算机科学,2000,(03)：1-3.
69.肖昕,陈奕,罗文永等.单粒活体稻谷种子直链淀粉含量的近红外透射光谱分析.中国水稻科学,2003,(03)：287-290
70.谢新华.稻米中直链淀粉和蛋白质含量的近红外透射光谱预测研究.[硕士学位论文].西北农林科技大学,2004
71.严衍禄.近红外光谱分析基础与应用.北京：中国轻工业出版社,2005
72.于润伟,朱晓慧.基于图像处理的稻米垩白自动检测研究.中国粮油学报,2007,22(1)：122-125
73.于晓娟,代冬岩,邓发强.模极大值法与尺度独立法在稻米边缘检测中的模拟研究.黑龙江八一农垦大学学报,2009,(03)：98-100
74.喻擎苍,严红滨.一种基于图像轮廓线的稻种模糊识别方法.农业工程学报,2002,18(1)：150-153
75.张聪,张慧.基于数学形态学的稻米粒形边缘检测研究.中国粮油学报,2007,22(5)：139-141
76.张静.几种检测大米新鲜度的方法比较.啤酒科技,2003,(8)：27-29
77.张永.基于模糊支持向量机的多类分类算法研究.[博士学位论文].大连：大连理工大学,2008
78.郑华东,刘木华,吴彦红等.基于计算机视觉的大米裂纹检测研究.农业工程学报,2006,22(7)：129-133
79.周福生.评价大米质量的基本内容.粮食科技与经济,1998,(5)：35-36
80.朱蔚萍,靳宏磊,叶桦等.二维灰度直方图上的距离判断分割方法.东南大学学报,1999,29(S)：16-19
81.诸小立,袁洪福,王艳斌等.近红外稳健分析校正模型的建立—样品温度的影响.光谱学与光谱分析,2004,24(6)：666-671
82.祝诗平,王一鸣,张小超等.基于遗传算法的近红外光谱谱区选择方法.农业机械学报,2004,35(5)：152-156
83.祝诗平,王一鸣,张小超等.近红外光谱建模异常样品剔除准则与方法.农业机械学报,2004,35(4)：115-119
84.祝晓芳,侯彩云,芮闯.基于计算机图像处理技术的黄粒米检测系统研究.粮油食品科技,2008,16(4)：6-8
85. Aggarwal A K, Mohan R. Aspect ratio analysis using image processing for rice grain quality. J Food Eng,2010,6(05):251-257
86. Bo-Jein K. The robustness of different statistical models for prediction of amylose content of rice based on near-infrared spectroscopy. J Agr As,2001,2(5):464-474
87. Camargo A, Smith. J S. Image pattern classification for the identification of disease causing agents in plants. Comp Electr Agr,2009,66:121-125
88. Chen C L, Chen T F. Analysing the freshness of intact rice grains by colour determination of peroxidase activity. J Sci FoodAgr,2003,83(12):1214-1218
89. Chen J H, Guan Z X, Sun C X et al. Inspection of rice appearance quality using machine vision. Proceedings of the 2009 WRI Global Congress on Intelligent Systems,2009, China
90. Cho K, Meer P. Image segmentation from consensus information. Comp Vis Im Und,1997,68(1):72-89
91. Christiane C, Fertig, Fridrun P, Roger D. Feasibility study for the rapid determination of the amylose content in starch by near-infrared spectroscopy. Eur J Pharm Sci,2004,21:155-159
92. Cozzolino D, Fassio A, Restaino E, et al. Verification of silage type using near-infrared spectroscopy combined with multivariate analysis. Journal of Agr and Food Chem,2008,56 (1):79-83
93. David M, Haaland, Edward V, Thomas. Partial least-squares methods for spectral analyses:Relation to other quantitaive calibration methods and the extraction of qualitative information. An Chem,1988,60 (11):1193-1202
94. Delwiche S R, Bean M M. Apparent amylose content of milled rice by near-inf rared reflectance spectrophotometry. Cer Chem,1995,72(2):182-187
95. Emadzadeh B, Razavi S M A, Farahmandfar R. Monitoring geometric characteristics of rice during processing by image analysis system and micrometer measurement. Int Agrophys,2010,24(l):21-27
96. Fuller M P, Ritter G L, Draper C S. Partial least squares quantitative analysis of infrared spectroscopic data. Part I:Algorithm implementation. Appl Spectr,1988, 42 (2):217-227
97. Gao H, Wang Y Q, Ge P J. Rice shape parameter detection based on image processing.1st International Conference on Computer and Computing Technologies in Agriculture,2007, China
98. Hachiya M, Asanome N, Goto T et al. Fluorescence Imaging with UV-Excitation for Evaluating Freshness of Rice. JARQ-Jpn Agr Res Q,2009,43(3):193-198
99. Jinorose M, Prachayawarakorn S, Soponronnarit S. Development of a computer vision system and novel evaluation criteria to characterize color and appearance of rice. Dry Tech,2010,28(9):1118-1124
100.Jouan R, Imbaud D, Bouveresse E, Massart D L, et al. Detection of prediction outliers and inliers in multivariate calibration. An Chim Acta,1999,388(3): 283-301
101.Khazaei J, Golpour I, Gholami A. Paddy rice varieties recognition using computer vision and neural networks.2010 International Conference on Agricultural and Animal Science,2010, Singapore
102.Lan Y, Fang Q, Kocher M F, Hanna M A. Detection of fissures in rice grains using imaging enhancement. Int J Food Prop,2002,5(01):205-215
103.Lee J C, Yoon Y H, Kim S M, Pyo B S, Hsieh F H, Kim H J, Eun J B, Rapid prediction of amylose content of polished rice by Fourier transform near-infrared spectroscopy. Food Sci Biotech,2007,16(3):477-481
104.Li D Y, Han J W, Shi X M, Chan M C. Knowledge representation and discovery based on linguistic atoms. J Knowledge-Based Syst,1998(10):431-440
105.Lin P, Chen, Y M, Bao Y D, He Y. Image detection of rice fissures using biorthogonal B-Spline wavelets in multi-resolution spaces. Food Biop Tech,2010, (06):1-8
106.Liu C C, Shaw J T, Poong K Y, et al. Classifying paddy rice by morphological and color features using machine vision. Cer Che,2005,82(06):649-653
107.Liu G R. Rice color inspection based on image processing technique. International Conference on Advances in Energy Engineering,2010, China
108.Lleti R, Melendeza E, OrtizM C, et al. Outliers in partial least squares regression application to calibration of wine grade with mean infrared data. An Chim Acta, 2005,544(1):60-701
109.Manickavasagan A, Sathya G et al. Comparison of illuminations to identify wheat classes using monochrome images. Comp El Agr,2008,63(2):237-244
110.Matsukura U, Kaneko S, Momma M. Method for measuring the freshness of individual rice grains by means of a color reaction of catalase activity. Nippon Shokuhin Kagaku Kogaku Kaishi,2000,47(7):523-528
111.Otsu N. A threshold selection method from gray-level histograms. IEEE T Syst Man Cy,1979,9(1):62-66
112.Pan M S, Tang J T, Yang X L. An Adaptive Median Filter Algorithm Based on B-spline Function. intl J Aut Comp,2011,8(1):92-99
113.Randall Mutters. Producing high quality rice for export market. USDA,2002.
114.Rittiron R, Saranwong S, Kawano S, Useful tips for constructing a near infrared-based quality sorting system for single brown-rice kernels. J Near Infrared Spectrosc.2004,(12):133-139
115.Sakai N, Yonekawa S, Matsuzaki A, et al. Two-dimensional image analysis of the shape of rice and its application to separating. J Food Eng,1996,27(04):397-407
116.Sansomboonsuk S, Afzulpurkar N. A computer vision system for rice kernel quality evaluation.16th International Symposium of the Danube-Adria-Association-for-Automation-and-Manufacturing,2005, Opatija, Croatia
117.Shao Y, Zhao C, He Y, Bao Y. Application of infrared spectroscopy technique and chemometrics for measurement of components in rice after radiation. Trans ASABE, 2009,52(1):187-192
118.Shimizu N, Okadome H, Yanagisawa T, Andren H, Thente K, Kimura T, Ohtsubo K. Application of visible/near-infrared transmittance spectroscopy for the improvement of amylose determination accuracy. Food Sci Tech Res,2003,9(2): 134-136
119.Shindo S, Takahashi S, Kobayashi M. A novel method for the determination of freshness of rice by acidification power test. Nippon Shokuhin Kagaku Kogaku Kaishi,2000,47(3):260-263
120.Takeda F, Uchida H, Tsuzuki T et al. A proposal of grading system for fallen rice using neural network. IEEE International Joint Conference on Neural Networks, 2002
121. Van D, Gerard. Colour analysis of rice using flatbed scanning and image Analysis 3rd European Conference on Colour in Graphics, Imaging, and Vision,2006
122.Vapnik V, Lerner A. Pattern recognition using generalized portrait. Aut Rem Contr, 1963,24 (6):774-780
123.Vapnik V. Statistical Learning Theory, Wiley, NY,1998
124.Verma B. Image processing techniques for grading and classification of rice. International Conference on Computer and Communication Technology,2010, India
125.Villarel C P, Cruz N M, Juliano B O. Rice amylose analysis by nearinfrared transmitance spect roscopy. Cer Chem,1994, (71):292-296
126.Visen N S, Shashidhar N S, Paliwal J, et al. Identification and segmentation of occluding groups of grain kernels in a grain sample image. JAgrie Eng Res,2001, 79(2):159-166
127.Walczak B, Massart D L. Robust principal components regression as a detection tool for outliers. Chem and Int Lab Syst,1995,27(1):41-54
128.Wan Y N, Lin C M, Chiou J F. Rice quality classification using an automatic grain quality inspection system. Tran ASAE,2002,45(2):379-387
129. Wan Y N. Adaptive classification method for an automatic grain quality inspection system using machine vision and neural network. ASAE Annual International Meeting,2000.
130. Wee C Y, Paramesran R, Takeda F. Sorting of rice grains using zernike moments. J Real time Im Proc,2009,4(04):353-363
131.Wu J G, Shi C H. Prediction of grain weight, brown rice weight and amylose content in single rice grains using near-infrared reflectance spectroscopy. Field Crops Res,2004,87(1):13-21
132.Xu L Z, Li Y M. Multi-Scale edge detection of rice internal damage based on computer vision. IEEE International Conference on Automation and Logistics, 2008, Qingdao, China
133.Xu L Z, Li Y M. Detection of stress cracks in rice kernels based on machine vision. Agr Mech in Asia, Africa and Latin America,2009,40(4):38-41
134.Yosuke Y, Hiroyoshi I, Minako T et al. Chalkiness in rice:Potential for evaluation with image analysis. Crop sci,2007,41(05):2113-2120
135.Zadeh L A. Fuzzysets. Inf Contr,1965, (8):338-353
136.Zhang Q, Yang W, Howard L, et al. Tracing fissure information by scanning elect ron m icro scopy characterization of naturally fissured surfaces of rice kernels. Trans ASAE,2003,46(6):1583-1588